<?xml version="1.0" encoding="ISO-8859-1"?><article xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance">
<front>
<journal-meta>
<journal-id>0123-7799</journal-id>
<journal-title><![CDATA[TecnoLógicas]]></journal-title>
<abbrev-journal-title><![CDATA[TecnoL.]]></abbrev-journal-title>
<issn>0123-7799</issn>
<publisher>
<publisher-name><![CDATA[Instituto Tecnológico Metropolitano - ITM]]></publisher-name>
</publisher>
</journal-meta>
<article-meta>
<article-id>S0123-77992021000300176</article-id>
<article-id pub-id-type="doi">10.22430/22565337.2132</article-id>
<title-group>
<article-title xml:lang="es"><![CDATA[Segmentación multinivel de patrones de Gleason usando representaciones convolucionales en imágenes histopatológicas]]></article-title>
<article-title xml:lang="en"><![CDATA[Multilevel Segmentation of Gleason Patterns using Convolutional Representations in Histopathological Images]]></article-title>
</title-group>
<contrib-group>
<contrib contrib-type="author">
<name>
<surname><![CDATA[Gómez]]></surname>
<given-names><![CDATA[Andrés]]></given-names>
</name>
<xref ref-type="aff" rid="Aff"/>
</contrib>
<contrib contrib-type="author">
<name>
<surname><![CDATA[León-Pérez]]></surname>
<given-names><![CDATA[Fabián]]></given-names>
</name>
<xref ref-type="aff" rid="Aff"/>
</contrib>
<contrib contrib-type="author">
<name>
<surname><![CDATA[Plazas-Wadynski]]></surname>
<given-names><![CDATA[Miguel]]></given-names>
</name>
<xref ref-type="aff" rid="Aff"/>
</contrib>
<contrib contrib-type="author">
<name>
<surname><![CDATA[Martínez-Carrillo]]></surname>
<given-names><![CDATA[Fabio]]></given-names>
</name>
<xref ref-type="aff" rid="Aff"/>
</contrib>
</contrib-group>
<aff id="Af1">
<institution><![CDATA[,Universidad Industrial de Santander  ]]></institution>
<addr-line><![CDATA[Bucaramanga ]]></addr-line>
<country>Colombia</country>
</aff>
<aff id="Af2">
<institution><![CDATA[,Universidad Industrial de Santander  ]]></institution>
<addr-line><![CDATA[Bucaramanga ]]></addr-line>
<country>Colombia</country>
</aff>
<aff id="Af3">
<institution><![CDATA[,Universidad Industrial de Santander  ]]></institution>
<addr-line><![CDATA[Bucaramanga ]]></addr-line>
<country>Colombia</country>
</aff>
<aff id="Af4">
<institution><![CDATA[,Universidad Industrial de Santander  ]]></institution>
<addr-line><![CDATA[Bucaramanga ]]></addr-line>
<country>Colombia</country>
</aff>
<pub-date pub-type="pub">
<day>00</day>
<month>12</month>
<year>2021</year>
</pub-date>
<pub-date pub-type="epub">
<day>00</day>
<month>12</month>
<year>2021</year>
</pub-date>
<volume>24</volume>
<numero>52</numero>
<fpage>176</fpage>
<lpage>196</lpage>
<copyright-statement/>
<copyright-year/>
<self-uri xlink:href="http://www.scielo.org.co/scielo.php?script=sci_arttext&amp;pid=S0123-77992021000300176&amp;lng=en&amp;nrm=iso"></self-uri><self-uri xlink:href="http://www.scielo.org.co/scielo.php?script=sci_abstract&amp;pid=S0123-77992021000300176&amp;lng=en&amp;nrm=iso"></self-uri><self-uri xlink:href="http://www.scielo.org.co/scielo.php?script=sci_pdf&amp;pid=S0123-77992021000300176&amp;lng=en&amp;nrm=iso"></self-uri><abstract abstract-type="short" xml:lang="es"><p><![CDATA[Resumen El sistema de puntuación de Gleason es el más utilizado para diagnosticar y cuantificar la agresividad del cáncer de próstata, estratificando regionalmente patrones anormales en imágenes histológicas. A pesar de ello, estudios recientes han reportado valores moderados de concordancia de 0.55, según el valor kappa en el diagnóstico de la enfermedad. Este estudio introduce una representación convolucional para la segmentación y estratificación semántica de regiones en imágenes histológicas implementando la puntuación de Gleason y tres niveles de representación. Para ello, en un primer nivel, se entrenó una red regional de tipo Mask R-CNN con anotaciones completas, lo que permitió definir delineaciones regionales, siendo efectivo en localizaciones con estructuras generales. En un segundo nivel, usando la misma arquitectura, se entrenó un modelo únicamente con anotaciones superpuestas del primer esquema, y que constituyen regiones con dificultad de clasificación. Finalmente, un tercer nivel de representación permitió una descripción más granular de las regiones, considerando las regiones resultantes de las activaciones del primer nivel. La segmentación final resultó de la superposición de los tres niveles de representación. La estrategia propuesta se validó y entrenó en un conjunto público con 886 imágenes histológicas. Las segmentaciones así generadas alcanzaron una media del Área Bajo la Curva de Precisión-Recalificación (AUPRC) de 0.8 ± 0.18 y 0.76 ± 0.15 respecto a los diagnósticos de dos patólogos, respectivamente. Los resultados muestran niveles de intersección regional cercanos a los de los patólogos de referencia. La estrategia propuesta es una herramienta potencial para ser implementada en el apoyo y análisis clínico.]]></p></abstract>
<abstract abstract-type="short" xml:lang="en"><p><![CDATA[Abstract The Gleason score is the most widely used grading system to diagnose and quantify the aggressiveness of prostate cancer, stratifying regional abnormal patterns on histological images. Nonetheless, recent studies into the Gleason score have reported moderate concordance values of 0.55 (kappa value) in the diagnosis of the disease. This study introduces a convolutional representation for the semantic segmentation and stratification of regions in histological images implementing the Gleason score and three levels of representation. On the first level, a regional network of the Mask R-CNN type is trained with complete annotations to define regional delineations, being effective in locations with general structures. On the second level, using the same architecture, a model is trained only with overlapping annotations from the first scheme, which are difficult-to-classify regions. Finally, a third level of representation produces a more granular description of the regions, considering the regions resulting from the activations of the first level. The final segmentation results from the superposition of the three levels of representation. The proposed strategy was validated and trained on a public set with 886 histological images. The segmentations thus generated achieved an average Area Under the Precision-Recall Curve (AUPRC) of 0.8 ± 0.18 and 0.76 ± 0.15 regarding the diagnoses of two pathologists, respectively. The results show regional intersection levels close to those of the reference pathologists. The proposed strategy is a potential tool to be implemented in clinical support and analysis.]]></p></abstract>
<kwd-group>
<kwd lng="es"><![CDATA[Segmentación semántica]]></kwd>
<kwd lng="es"><![CDATA[aprendizaje profundo]]></kwd>
<kwd lng="es"><![CDATA[puntuación de Gleason]]></kwd>
<kwd lng="es"><![CDATA[imágenes histopatológicas]]></kwd>
<kwd lng="es"><![CDATA[cáncer de próstata]]></kwd>
<kwd lng="en"><![CDATA[Semantic segmentation]]></kwd>
<kwd lng="en"><![CDATA[deep learning]]></kwd>
<kwd lng="en"><![CDATA[Gleason score]]></kwd>
<kwd lng="en"><![CDATA[histopathological images]]></kwd>
<kwd lng="en"><![CDATA[prostate cancer]]></kwd>
</kwd-group>
</article-meta>
</front><back>
<ref-list>
<ref id="B1">
<label>[1]</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Bray]]></surname>
<given-names><![CDATA[F.]]></given-names>
</name>
<name>
<surname><![CDATA[Ferlay]]></surname>
<given-names><![CDATA[J.]]></given-names>
</name>
<name>
<surname><![CDATA[Soerjomataram]]></surname>
<given-names><![CDATA[I.]]></given-names>
</name>
<name>
<surname><![CDATA[Siegel]]></surname>
<given-names><![CDATA[R. L.]]></given-names>
</name>
<name>
<surname><![CDATA[Torre]]></surname>
<given-names><![CDATA[L. A.]]></given-names>
</name>
<name>
<surname><![CDATA[Jemal]]></surname>
<given-names><![CDATA[A.]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Global cancer statistics 2018: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries]]></article-title>
<source><![CDATA[CA: A Cancer j. Clinic.]]></source>
<year>2018</year>
<volume>68</volume>
<numero>6</numero>
<issue>6</issue>
<page-range>394-424</page-range></nlm-citation>
</ref>
<ref id="B2">
<label>[2]</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Bley]]></surname>
<given-names><![CDATA[E.]]></given-names>
</name>
<name>
<surname><![CDATA[Silva]]></surname>
<given-names><![CDATA[A.]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Diagnóstico precoz del cáncer de próstata]]></article-title>
<source><![CDATA[Rev.Méd. Clín. Las Condes]]></source>
<year>2011</year>
<volume>22</volume>
<numero>4</numero>
<issue>4</issue>
<page-range>453-8</page-range></nlm-citation>
</ref>
<ref id="B3">
<label>[3]</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Ruiz López]]></surname>
<given-names><![CDATA[A. I.]]></given-names>
</name>
<name>
<surname><![CDATA[Pérez Mesa]]></surname>
<given-names><![CDATA[J. C.]]></given-names>
</name>
<name>
<surname><![CDATA[Cruz Batista]]></surname>
<given-names><![CDATA[Y.]]></given-names>
</name>
<name>
<surname><![CDATA[González Lorenzo]]></surname>
<given-names><![CDATA[L. E.]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Actualización sobre cáncer de próstata]]></article-title>
<source><![CDATA[ccm]]></source>
<year>2017</year>
<volume>21</volume>
<numero>3</numero>
<issue>3</issue>
</nlm-citation>
</ref>
<ref id="B4">
<label>[4]</label><nlm-citation citation-type="">
<collab>American Cancer Society</collab>
<source><![CDATA[Pruebas para diagnosticar y determinar la etapa del cáncer de próstata]]></source>
<year>2019</year>
</nlm-citation>
</ref>
<ref id="B5">
<label>[5]</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Griffiths]]></surname>
<given-names><![CDATA[D. F. R.]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[A study of Gleason score interpretation in different groups of UK pathologists; techniques for improving reproducibility]]></article-title>
<source><![CDATA[Histopathology]]></source>
<year>2006</year>
<volume>48</volume>
<numero>6</numero>
<issue>6</issue>
<page-range>655-62</page-range></nlm-citation>
</ref>
<ref id="B6">
<label>[6]</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Coard]]></surname>
<given-names><![CDATA[K. C.]]></given-names>
</name>
<name>
<surname><![CDATA[Freeman]]></surname>
<given-names><![CDATA[V. L.]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Gleason Grading of Prostate Cancer: Level of Concordance Between Pathologists at the University Hospital of the West Indies]]></article-title>
<source><![CDATA[Am. J. Clin. Pathol]]></source>
<year>2004</year>
<volume>122</volume>
<numero>3</numero>
<issue>3</issue>
<page-range>373-6</page-range></nlm-citation>
</ref>
<ref id="B7">
<label>[7]</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[McLean]]></surname>
<given-names><![CDATA[M.]]></given-names>
</name>
<name>
<surname><![CDATA[Srigley]]></surname>
<given-names><![CDATA[J.]]></given-names>
</name>
<name>
<surname><![CDATA[Banerjee]]></surname>
<given-names><![CDATA[D.]]></given-names>
</name>
<name>
<surname><![CDATA[Warde]]></surname>
<given-names><![CDATA[P.]]></given-names>
</name>
<name>
<surname><![CDATA[Hao]]></surname>
<given-names><![CDATA[Y.]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Interobserver variation in prostate cancer gleason scoring: Are there implications for the design of clinical trials and treatment strategies?]]></article-title>
<source><![CDATA[Clin. Oncol]]></source>
<year>1997</year>
<volume>9</volume>
<numero>4</numero>
<issue>4</issue>
<page-range>222-5</page-range></nlm-citation>
</ref>
<ref id="B8">
<label>[8]</label><nlm-citation citation-type="confpro">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Doyle]]></surname>
<given-names><![CDATA[S.]]></given-names>
</name>
<name>
<surname><![CDATA[Hwang]]></surname>
<given-names><![CDATA[M.]]></given-names>
</name>
<name>
<surname><![CDATA[Shah]]></surname>
<given-names><![CDATA[K.]]></given-names>
</name>
<name>
<surname><![CDATA[Madabhushi]]></surname>
<given-names><![CDATA[A.]]></given-names>
</name>
<name>
<surname><![CDATA[Feldman]]></surname>
<given-names><![CDATA[M.]]></given-names>
</name>
<name>
<surname><![CDATA[Tomaszeweski]]></surname>
<given-names><![CDATA[J.]]></given-names>
</name>
</person-group>
<source><![CDATA[Automated grading of prostate cancer using architectural and textural image features]]></source>
<year></year>
<conf-name><![CDATA[ 4th IEEE Inter. Symp. Biomed. Imaging: From Nano to Macro]]></conf-name>
<conf-date>2007</conf-date>
<conf-loc>Arlington </conf-loc>
<page-range>1284-7</page-range></nlm-citation>
</ref>
<ref id="B9">
<label>[9]</label><nlm-citation citation-type="book">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Doyle]]></surname>
<given-names><![CDATA[S.]]></given-names>
</name>
<name>
<surname><![CDATA[Madabhushi]]></surname>
<given-names><![CDATA[A.]]></given-names>
</name>
<name>
<surname><![CDATA[Feldman]]></surname>
<given-names><![CDATA[M.]]></given-names>
</name>
<name>
<surname><![CDATA[Tomaszeweski]]></surname>
<given-names><![CDATA[John]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[A boosting cascade for automated detection of prostate cancer from digitized histology]]></article-title>
<person-group person-group-type="editor">
<name>
<surname><![CDATA[Larsen]]></surname>
<given-names><![CDATA[R.]]></given-names>
</name>
<name>
<surname><![CDATA[Nielsen]]></surname>
<given-names><![CDATA[M.]]></given-names>
</name>
</person-group>
<source><![CDATA[Medical Image Computing and Computer-Assisted Intervention]]></source>
<year>2006</year>
<publisher-name><![CDATA[Sporring, Eds]]></publisher-name>
</nlm-citation>
</ref>
<ref id="B10">
<label>[10]</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Farjam]]></surname>
<given-names><![CDATA[R.]]></given-names>
</name>
<name>
<surname><![CDATA[Soltanian-Zadeh]]></surname>
<given-names><![CDATA[H.]]></given-names>
</name>
<name>
<surname><![CDATA[Jafari-Khouzani]]></surname>
<given-names><![CDATA[K.]]></given-names>
</name>
<name>
<surname><![CDATA[Zoroofi]]></surname>
<given-names><![CDATA[R. A.]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[An image analysis approach for automatic malignancy determination of prostate pathological images]]></article-title>
<source><![CDATA[Cytom. Part B Clin. Cytom.]]></source>
<year>2007</year>
<volume>72B</volume>
<numero>4</numero>
<issue>4</issue>
<page-range>227-40</page-range></nlm-citation>
</ref>
<ref id="B11">
<label>[11]</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Arvaniti]]></surname>
<given-names><![CDATA[E.]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Automated Gleason grading of prostate cancer tissue microarrays via deep learning]]></article-title>
<source><![CDATA[Scientific reports]]></source>
<year>2018</year>
<volume>8</volume>
</nlm-citation>
</ref>
<ref id="B12">
<label>[12]</label><nlm-citation citation-type="confpro">
<person-group person-group-type="author">
<name>
<surname><![CDATA[León]]></surname>
<given-names><![CDATA[F.]]></given-names>
</name>
<name>
<surname><![CDATA[Plazas]]></surname>
<given-names><![CDATA[M.]]></given-names>
</name>
<name>
<surname><![CDATA[Martínez]]></surname>
<given-names><![CDATA[F.]]></given-names>
</name>
</person-group>
<source><![CDATA[An inception deep architecture to differentiate close-related Gleason prostate cancer scores]]></source>
<year></year>
<conf-name><![CDATA[ 15th Inter. Symp. Med. Info. Proces. Anal]]></conf-name>
<conf-date>2019</conf-date>
<conf-loc>Medellín </conf-loc>
</nlm-citation>
</ref>
<ref id="B13">
<label>[13]</label><nlm-citation citation-type="book">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Payá Bosch]]></surname>
<given-names><![CDATA[E.]]></given-names>
</name>
</person-group>
<source><![CDATA[Diseño y desarrollo de un sistema automático de segmentación de glándulas histológicas para identificar el cáncer de próstata en una etapa inicial]]></source>
<year>2019</year>
<publisher-name><![CDATA[Univ. Pol. Valencia]]></publisher-name>
</nlm-citation>
</ref>
<ref id="B14">
<label>[14]</label><nlm-citation citation-type="book">
<person-group person-group-type="author">
<name>
<surname><![CDATA[García Pardo]]></surname>
<given-names><![CDATA[J. G.]]></given-names>
</name>
</person-group>
<source><![CDATA[Diseño y desarrollo de un sistema automático de clasificación de estructuras glandulares en imágenes histológicas de próstata]]></source>
<year>2018</year>
<publisher-name><![CDATA[Univ. Pol. Valencia]]></publisher-name>
</nlm-citation>
</ref>
<ref id="B15">
<label>[15]</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Bulten]]></surname>
<given-names><![CDATA[W.]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Automated deep- learning system for Gleason grading of prostate cancer using biopsies: A diagnostic study]]></article-title>
<source><![CDATA[Lancet Oncol]]></source>
<year>2020</year>
<volume>21</volume>
<numero>2</numero>
<issue>2</issue>
<page-range>233-42</page-range></nlm-citation>
</ref>
<ref id="B16">
<label>[16]</label><nlm-citation citation-type="">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Nathan]]></surname>
<given-names><![CDATA[I.]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Semantic segmentation for prostate cancer grading by convolutional neural networks]]></article-title>
<source><![CDATA[Medical Imaging 2018: Digital Pathology]]></source>
<year>2018</year>
<publisher-loc><![CDATA[Houston ]]></publisher-loc>
</nlm-citation>
</ref>
<ref id="B17">
<label>[17]</label><nlm-citation citation-type="confpro">
<person-group person-group-type="author">
<name>
<surname><![CDATA[He]]></surname>
<given-names><![CDATA[K.]]></given-names>
</name>
<name>
<surname><![CDATA[Gkioxari]]></surname>
<given-names><![CDATA[G.]]></given-names>
</name>
<name>
<surname><![CDATA[Dollár]]></surname>
<given-names><![CDATA[P.]]></given-names>
</name>
<name>
<surname><![CDATA[Girshick]]></surname>
<given-names><![CDATA[R.]]></given-names>
</name>
</person-group>
<source><![CDATA[Mask r-cnn]]></source>
<year></year>
<conf-name><![CDATA[ Proc. IEEE Inter. Conf. Computer vision]]></conf-name>
<conf-date>2017</conf-date>
<conf-loc>Venice </conf-loc>
</nlm-citation>
</ref>
<ref id="B18">
<label>[18]</label><nlm-citation citation-type="confpro">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Babenko Yandex]]></surname>
<given-names><![CDATA[A.]]></given-names>
</name>
<name>
<surname><![CDATA[Lempitsky]]></surname>
<given-names><![CDATA[V.]]></given-names>
</name>
</person-group>
<source><![CDATA[Aggregating local deep features for image retrieval]]></source>
<year></year>
<conf-name><![CDATA[ 2015 IEEE Inter, Conf. Comp. Vision (ICCV))]]></conf-name>
<conf-date>2015</conf-date>
<conf-loc> </conf-loc>
</nlm-citation>
</ref>
<ref id="B19">
<label>[19]</label><nlm-citation citation-type="confpro">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Kalantidis]]></surname>
<given-names><![CDATA[Y.]]></given-names>
</name>
<name>
<surname><![CDATA[Mellina]]></surname>
<given-names><![CDATA[C.]]></given-names>
</name>
<name>
<surname><![CDATA[Osindero]]></surname>
<given-names><![CDATA[S.]]></given-names>
</name>
</person-group>
<source><![CDATA[Crossdimensional weighting for aggregated deep convolutional features]]></source>
<year></year>
<conf-name><![CDATA[ European conference on computer vision, Lecture Notes in Computer Science, 9913]]></conf-name>
<conf-date>2016</conf-date>
<conf-loc>Cham </conf-loc>
</nlm-citation>
</ref>
<ref id="B20">
<label>[20]</label><nlm-citation citation-type="">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Arvaniti]]></surname>
<given-names><![CDATA[E.]]></given-names>
</name>
</person-group>
<source><![CDATA[Replication data for: Automated Gleason grading of prostate cancer tissue microarrays via deep learning]]></source>
<year>2018</year>
</nlm-citation>
</ref>
<ref id="B21">
<label>[21]</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Zhong]]></surname>
<given-names><![CDATA[Q.]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[A curated collection of tissue microarray images and clinical outcome data of prostate cancer patients]]></article-title>
<source><![CDATA[Scientific data]]></source>
<year>2017</year>
<volume>4</volume>
<page-range>170014</page-range></nlm-citation>
</ref>
<ref id="B22">
<label>[22]</label><nlm-citation citation-type="">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Tsung-Yi]]></surname>
<given-names><![CDATA[L.]]></given-names>
</name>
</person-group>
<source><![CDATA[COCO API - Dataset]]></source>
<year>2020</year>
</nlm-citation>
</ref>
<ref id="B23">
<label>[23]</label><nlm-citation citation-type="book">
<person-group person-group-type="author">
<name>
<surname><![CDATA[García Seisdedos]]></surname>
<given-names><![CDATA[D.]]></given-names>
</name>
</person-group>
<source><![CDATA[Segmentación de núcleos celulares en imágenes de microscopía ayudados por redes neuronales convolucionales]]></source>
<year>2018</year>
<publisher-name><![CDATA[Univ. Oberta Catalunya]]></publisher-name>
</nlm-citation>
</ref>
<ref id="B24">
<label>[24]</label><nlm-citation citation-type="book">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Marín Soto]]></surname>
<given-names><![CDATA[D.]]></given-names>
</name>
</person-group>
<source><![CDATA[Segmentación de células mediante técnicas de Procesamiento Digital de Imágenes para el rastreo de células cancerosas]]></source>
<year>2018</year>
<publisher-name><![CDATA[Inst. Tec. Costa Rica]]></publisher-name>
</nlm-citation>
</ref>
<ref id="B25">
<label>[25]</label><nlm-citation citation-type="book">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Henderson]]></surname>
<given-names><![CDATA[P.]]></given-names>
</name>
<name>
<surname><![CDATA[Ferrari]]></surname>
<given-names><![CDATA[V.]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[End-to-End Training of Object Class Detectors for Mean Average Precision]]></article-title>
<source><![CDATA[Lecture Notes in Computer Science]]></source>
<year>2017</year>
<volume>10115</volume>
<page-range>198-213</page-range><publisher-loc><![CDATA[Cham ]]></publisher-loc>
<publisher-name><![CDATA[Springer]]></publisher-name>
</nlm-citation>
</ref>
<ref id="B26">
<label>[26]</label><nlm-citation citation-type="book">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Boyd]]></surname>
<given-names><![CDATA[K.]]></given-names>
</name>
<name>
<surname><![CDATA[Eng]]></surname>
<given-names><![CDATA[K. H.]]></given-names>
</name>
<name>
<surname><![CDATA[Page]]></surname>
<given-names><![CDATA[C. D.]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Area under the Precision-Recall Curve: Point Estimates and Confidence Intervals]]></article-title>
<source><![CDATA[Lecture Notes in Computer Science]]></source>
<year>2013</year>
<volume>8190</volume>
<publisher-loc><![CDATA[Berlin, Heidelberg ]]></publisher-loc>
<publisher-name><![CDATA[Springer]]></publisher-name>
</nlm-citation>
</ref>
</ref-list>
</back>
</article>
